CVE-2026-5970

HIGH

A vulnerability was detected in FoundationAgents MetaGPT up to 0.8.1. This affects the function check_solution of the component HumanEvalBenchmark/MBPPBenchmark. Performing a manipulation results in code injection. The attack may be initiated remotely. The exploit is now public and may be used. The project was informed of the problem early through a pull request but has not reacted yet.

CVSS v3.1 Score

7.3
HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L
Attack Vector
NETWORK
Complexity
LOW
Privileges
NONE
User Interaction
NONE
Scope
UNCHANGED
Confidentiality
LOW
Integrity
LOW
Availability
LOW
Published: 4/9/2026Modified: 6/17/2026

Related Intelligence (0)

No articles currently reference this CVE.

References (6)

https://github.com/FoundationAgents/MetaGPT/Producthttps://github.com/FoundationAgents/MetaGPT/issues/1942ExploitIssue Trackinghttps://github.com/FoundationAgents/MetaGPT/pull/1988Issue TrackingPatchhttps://vuldb.com/submit/791693ExploitThird Party Advisoryhttps://vuldb.com/vuln/356524Third Party AdvisoryVDB Entryhttps://vuldb.com/vuln/356524/ctiPermissions RequiredVDB Entry